[SimplifyCFG] Relax cttz cost check in simplifySwitchOfPowersOfTwo

We should be able to allow `simplifySwitchOfPowersOfTwo` transform
to take place, as, on recent X86 targets, the weighted latency-size
appears to be 2. This favours computing trailing zeroes and indexing
into a smaller value table, over generating a jump table with an
indirect branch (which overall should be more efficient).

Author: antoniofrighetto

llvm/lib/Transforms/Utils/SimplifyCFG.cpp

@@ -7198,8 +7198,10 @@ static bool reduceSwitchRange(SwitchInst *SI, IRBuilder<> &Builder,
 /// will be transformed to:
 /// switch (count_trailing_zeros(C)) { case 0: case 1: case 6: case 7: }
 ///
-/// This transformation allows better lowering and could allow transforming into
-/// a lookup table.
+/// This transformation allows better lowering and may transform the switch
+/// instruction into a sequence of bit manipulation and a smaller
+/// log2(C)-indexed value table (instead of traditionally emitting a load of the
+/// address of the jump target, and indirectly jump to it).
 static bool simplifySwitchOfPowersOfTwo(SwitchInst *SI, IRBuilder<> &Builder,
                                         const DataLayout &DL,
                                         const TargetTransformInfo &TTI) {
@@ -7211,17 +7213,15 @@ static bool simplifySwitchOfPowersOfTwo(SwitchInst *SI, IRBuilder<> &Builder,
       !DL.fitsInLegalInteger(CondTy->getIntegerBitWidth()))
     return false;
 
-  const auto CttzIntrinsicCost = TTI.getIntrinsicInstrCost(
-      IntrinsicCostAttributes(Intrinsic::cttz, CondTy,
-                              {Condition, ConstantInt::getTrue(Context)}),
-      TTI::TCK_SizeAndLatency);
-
-  if (CttzIntrinsicCost > TTI::TCC_Basic)
-    // Inserting intrinsic is too expensive.
+  // Ensure trailing zeroes count intrinsic emission is not too expensive.
+  IntrinsicCostAttributes Attrs(Intrinsic::cttz, CondTy,
+                                {Condition, ConstantInt::getTrue(Context)});
+  if (TTI.getIntrinsicInstrCost(Attrs, TTI::TCK_SizeAndLatency) >
+      TTI::TCC_Basic * 2)
     return false;
 
   // Only bother with this optimization if there are more than 3 switch cases.
-  // SDAG will only bother creating jump tables for 4 or more cases.
+  // SDAG will start emitting jump tables for 4 or more cases.
   if (SI->getNumCases() < 4)
     return false;
 

llvm/test/Transforms/SimplifyCFG/X86/switch-of-powers-of-two.ll

@@ -6,25 +6,9 @@ target triple = "x86_64-unknown-linux-gnu"
 define i32 @switch_of_powers_two(i32 %arg) {
 ; CHECK-LABEL: @switch_of_powers_two(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    switch i32 [[ARG:%.*]], label [[DEFAULT_CASE:%.*]] [
-; CHECK-NEXT:      i32 1, label [[RETURN:%.*]]
-; CHECK-NEXT:      i32 8, label [[BB2:%.*]]
-; CHECK-NEXT:      i32 16, label [[BB3:%.*]]
-; CHECK-NEXT:      i32 32, label [[BB4:%.*]]
-; CHECK-NEXT:      i32 64, label [[BB5:%.*]]
-; CHECK-NEXT:    ]
-; CHECK:       default_case:
-; CHECK-NEXT:    unreachable
-; CHECK:       bb2:
-; CHECK-NEXT:    br label [[RETURN]]
-; CHECK:       bb3:
-; CHECK-NEXT:    br label [[RETURN]]
-; CHECK:       bb4:
-; CHECK-NEXT:    br label [[RETURN]]
-; CHECK:       bb5:
-; CHECK-NEXT:    br label [[RETURN]]
-; CHECK:       return:
-; CHECK-NEXT:    [[SWITCH_LOAD:%.*]] = phi i32 [ 2, [[BB2]] ], [ 1, [[BB3]] ], [ 0, [[BB4]] ], [ 42, [[BB5]] ], [ 3, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.cttz.i32(i32 [[ARG:%.*]], i1 true)
+; CHECK-NEXT:    [[SWITCH_GEP:%.*]] = getelementptr inbounds [7 x i32], ptr @switch.table.switch_of_powers_two, i32 0, i32 [[TMP0]]
+; CHECK-NEXT:    [[SWITCH_LOAD:%.*]] = load i32, ptr [[SWITCH_GEP]], align 4
 ; CHECK-NEXT:    ret i32 [[SWITCH_LOAD]]
 ;
 entry: